Q2_K_S GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 19715 models have a Q2_K_S file. Sizes run from 2M to 671B parameters. The longest trained context is 10240K tokens.

Most downloadedNewestLargestLongest contextSmallest
NE
NeutralWeirdness V1 24B Heretic
Neutralweirdness · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
QW
Sally QwQ
Qwen · mradermacher
Params32.8B
Context40K
Q4_K_M19.9 GB
ReasoningTool use
RO
RoboInter VLM
Robointer · mradermacher
Params7.6B
Context125K
Q4_K_M4.7 GB
Vision
HA
Harvey 9B
Harvey · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
QW
Qwen2.5 7B Instruct
Qwen · legraphista
Params7.62B
Context32K
Smallest1.9 GB
Tool use
PH
PhysX Omni
Physx · mradermacher
Params7.6B
Context125K
Q4_K_M4.7 GB
Vision
QW
Qwen3.8 2B Heretic Max
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool use
CN
CNY 14B
Cny · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Reasoning
AG
Agents A1
Agents · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
QW
ReSearch Qwen 7B
Qwen · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
QW
Qwen3.5 27B Unredacted MAX
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Reasoning
QV
QVikhr 3 8B Instruction
Qvikhr · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen2.5 1.5B VibeThinker Heretic Uncensored Abliterated
Qwen · mradermacher
Params1.54B
Context128K
Q4_K_M1.0 GB
GGUF
GP
Financial Gpt Oss 20b Q8
gpt-oss · mradermacher
Params20.9B
Context128K
Q4_K_M15.8 GB
GGUF
OR
Ornstein3.6 35B A3B SABER
Ornstein · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool use
MI
MiniCPM5 2B
MiniCPM · mradermacher
Params2.52B
Context128K
Q4_K_M1.6 GB
CodingTool use
QW
Qwen3.5 21B GLM 4.7 Flash Deckard Heretic Uncensored Thinking
Qwen · mradermacher
Params20.8B
Context256K
Q4_K_M12.9 GB
CodingReasoningRoleplay
GE
Gemma 4 E4B It OBLITERATED
Gemma · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
GGUF
GE
Gemma 3 27b It Ultra Uncensored Heretic
Gemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
GGUF
ZE
K1 v6 Zero
Zero · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Reasoning
XL
xLAM 7b R
Xlam · legraphista
Params7.24B
Context32K
Smallest1.6 GB
Tool use
GE
Gemma 4 31B It Mystery Fine Tune HERETIC UNCENSORED Thinking
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
CodingReasoningRoleplay
SP
RP Spectrum 24B
Spectrum · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
OL
OLMo 2 1124 7B SFT Preview
OLMo · mradermacher
Params7.3B
Context4K
Q4_K_M4.5 GB
GGUF
QW
Qwen3.5 35B A3B Gemini 3.1 Opus 4.6 Reasoning
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Reasoning
LL
Claude Llama 8B Think
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Reasoning
MI
Mira 12b
Mira · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningRoleplayTool use
QW
Qwen2.5 Coder 1.5B Instruct
Qwen · legraphista
Params1.54B
Context32K
Smallest0.4 GB
CodingTool use
QW
Qwen2.5 72B Instruct
Qwen · legraphista
Params72.7B
Context32K
Smallest23.7 GB
Tool use
QW
Huihui Qwen3.5 9B Abliterated Grimoire SimPO
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF

Other quants

Keep browsing